pdf Claude Code Skill
Claude Code SkillClaude CodeDocuments & Content CreationThe explanation below is AI-generated. Please verify it against the sources.
This skill gives Claude step-by-step guidance for working with PDF files, covering reading, text and table extraction, merging, splitting, rotating, watermarking, creating new documents, form filling, encryption and decryption, image extraction, and OCR on scanned pages. According to the SKILL.md instructions, it relies on local Python libraries such as pypdf, pdfplumber, and reportlab, plus command-line utilities like pdftotext, qpdf, and pdftk, rather than any external web service. The guide points to a separate file for detailed PDF form-filling steps and another reference file for more advanced or JavaScript-based techniques. It is intended to be invoked whenever a user's request involves a PDF file or producing one.
What you can do with pdf
- Extract text and tables from PDF documents
- Merge multiple PDFs into a single file or split a PDF into separate pages
- Rotate pages and apply watermarks
- Create new PDFs containing text, multiple pages, or structured layouts
- Fill in PDF form fields (with additional detail in a separate reference file)
- Encrypt PDFs with a password or decrypt existing encrypted files
- Extract embedded images from a PDF
- Run OCR on scanned PDF pages to produce searchable text